Determination of the clinical state of a subject

• US 20070010723A1
• Filed: 07/05/2005
• Published: 01/11/2007
• Est. Priority Date: 07/05/2005
• Status: Active Grant

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Virtanen, Juha, Huiku, Matti, Uutela, Kimmo
• Granted Patent: US 8,574,156 B2
• Time in Patent Office: Days
• US Class Current: 600/301
• CPC Class Codes: A61B 5/0006 ECG or EEG signals
• CPC Class Codes: A61B 5/0205 Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
• CPC Class Codes: A61B 5/021 Measuring pressure in heart or blood vessels A61B5/0205 takes precedence
• CPC Class Codes: A61B 5/02416 using photoplethysmograph signals, e.g. generated by infrared radiation A61B5/14552 takes precedence
• CPC Class Codes: A61B 5/0261 using optical means, e.g. infrared light
• CPC Class Codes: A61B 5/24 Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
• CPC Class Codes: A61B 5/30 Input circuits therefor
• CPC Class Codes: A61B 5/318 Heart-related electrical modalities, e.g. electrocardiography [ECG]
• CPC Class Codes: A61B 5/349 Detecting specific parameters of the electrocardiograph cycle
• CPC Class Codes: A61B 5/369 Electroencephalography [EEG] devices for psychotechnics A61B5/16
• CPC Class Codes: A61B 5/4035 Evaluating the autonomic nervous system
• CPC Class Codes: A61B 5/4821 Determining level or depth of anaesthesia A61B5/1106 takes precedence
• CPC Class Codes: A61B 5/4824 Touch or pain perception evaluation A61B5/4821 takes precedence
• CPC Class Codes: A61B 5/4839 combined with drug delivery
• CPC Class Codes: A61B 5/7275 Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• CPC Class Codes: A61B 5/7282 Event detection, e.g. detecting unique waveforms indicative of a medical condition A61B5/4094, A61B5/4818, A61B5/349, A61B5/0823 take precedence
• CPC Class Codes: G06F 2218/08 Feature extraction
• CPC Class Codes: G16H 40/63 for local operation
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems
• CPC Class Codes: G16H 50/30 for calculating health indices; for individual health risk assessment
• CPC Class Codes: Y10S 128/92 : Computer assisted medical diagnostics

Abstract

The invention relates to the determination of the clinical state of a subject. A respective adaptive transform is applied to at least one measurement signal acquired from the subject, each adaptive transform being dependent on previously acquired history data, and a diagnostic index is formed, which is dependent on the transformed measurement signal(s) and serves as a measure of the clinical state of the subject. In order to reliably evaluate the clinical state of a subject on a fixed diagnostic scale during changes in the state of the subject, some or all of the previously acquired history data on which an adaptive transform is currently dependent is replaced with other previously acquired history data when a predetermined event is detected. The predetermined event is indicative of a change in the respective measurement signal, and the introduction of the said other previously acquired history data sets the transform ready for the change.

Claims

1. A method for determining a clinical state of a subject, the method comprising the steps of:

acquiring at least one measurement signal containing physiological data from the subject;

subjecting the at least one measurement signal to an adaptive transform to obtain at least one transformed measurement signal, the adaptive transform being dependent on previously acquired history data;

forming a diagnostic index which is dependent on the at least one transformed measurement signal, the diagnostic index serving as a measure of the clinical state of the subject; and

replacing at least part of the previously acquired history data on which the adaptive transform is currently dependent with other previously acquired history data, the replacing step being performed when a predetermined event is detected.

2. A method according to claim 1, further comprising the steps of:

defining a set of at least two subject state categories into which the subject may be classified based on the subject'"'"'s current state;

acquiring category-specific history data for each of the at least two subject state categories; and

choosing at least one subject state category into which the subject is to be classified, said at least one subject state category being chosen from among the at least two subject state categories.

3. A method according to claim 2, wherein the predetermined event is detected when the at least one subject state category, into which the subject is to be classified changes.

4. A method according to claim 1, wherein the replacing step includes replacing at least part of the previously acquired history data on which the adaptive transform is currently dependent with other previously acquired history data, the other previously acquired history data comprising history data obtained from a group of subjects.

5. A method according to claim 4, wherein the replacing step further includes replacing at least part of the previously acquired history data on which the adaptive transform is currently dependent with other previously acquired history data, the other previously acquired history data comprising history data obtained from the subject during a predetermined preceding time period.

6. A method according to claim 5, further comprising the steps of decreasing the degree of dependence of the adaptive transform on the history data obtained from the group of subjects and increasing the degree of dependence of the adaptive transform on the history data obtained from the subject, wherein the decreasing and increasing steps are performed simultaneously.

7. A method according to claim 2, wherein the replacing step includes replacing at least part of the previously acquired history data on which the adaptive transform is currently dependent with other previously acquired history data, in which the other previously acquired history data comprises the category-specific history data acquired for the at least one subject state category.

8. A method according to claim 7, wherein the replacing step includes replacing at least part of the previously acquired history data on which the adaptive transform is currently dependent with other previously acquired history data, in which the other previously acquired history data comprises data derived from the category-specific history data acquired for more than one subject state categories.

9. A method according to claim 2, wherein

the defining step includes defining the set of subject state categories, including a wake state category indicating that the subject is conscious and a sleep state category indicating that the subject is unconscious;

and

the forming step includes forming the diagnostic index, in which the diagnostic index is indicative of the level of nociception in the subject.

10. A method according to claim 2, further comprising a step of displaying the diagnostic index for at least one of the subject state categories, in which the displaying step includes using visual information identifying the at least one of the subject state categories.

11. A method according to claim 1, wherein

the acquiring step includes acquiring at least two measurement signals from the subject, in which each of the at least two measurement signals is indicative of a respective physiological parameter, whereby at least two transformed measurement signals are obtained in the subjecting step;

and

the forming step includes forming the diagnostic index as a weighted average of the at least two transformed measurement signals.

12. A method according to claim 1, wherein the acquiring step includes

acquiring at least two physiological signals from the subject, each physiological signal being indicative of a respective physiological parameter;

and

producing the at least one measurement signal as a combined signal from the at least two physiological signals.

13. An apparatus for determining a clinical state of a subject, the apparatus comprising:

measurement means for acquiring at least one measurement signal containing physiological data from the subject;

transform means for subjecting at least one measurement signal to an adaptive transform to obtain at least one transformed measurement signal, the adaptive transform being dependent on previously acquired history data;

means for forming a diagnostic index which is dependent on the at least one transformed measurement signal, the diagnostic index serving as a measure of the clinical state of the subject;

first monitoring means for detecting a predetermined event; and

control means for replacing at least part of the previously acquired history data on which the adaptive transform is currently dependent with other previously acquired history data, the control means being responsive to the first monitoring means.

14. An apparatus according to claim 13, further comprising second monitoring means for choosing at least one predetermined subject state category into which the subject is to be classified based on the subject'"'"'s current state.

15. An apparatus according to claim 14, wherein the first monitoring means are responsive to the second monitoring means for detecting the predetermined event when the at least one predetermined subject state category changes.

16. An apparatus according to claim 14, wherein the other previously acquired history data which is replaced comprises data acquired for one predetermined subject state category.

17. An apparatus according to claim 14, wherein the other previously acquired history data which is replaced is derived from data acquired for at least two predetermined subject state categories.

18. An apparatus according to claim 13, wherein

the measurement means are configured to acquire at least two measurement signals from the subject, each of the at least two measurement signals being indicative of a respective physiological parameter;

the transform means are configured to subject the at least two measurement signals to at least two adaptive transforms, respectively, thereby to obtain at least two transformed measurement signals; and

the means for forming the diagnostic index are configured to produce a weighted average of the at least two transformed measurement signals.

19. An apparatus according to claim 13, wherein the measurement means are configured to acquire at least two physiological signals from the subject and to produce the at least one measurement signal as a combined signal from the at least two physiological signals, each physiological signal being indicative of a respective physiological parameter.

20. An apparatus for determining a clinical state of a subject, the apparatus comprising:

a measurement arrangement configured to acquire at least one measurement signal containing physiological data from the subject;

a signal processing unit configured to subject the measurement signal to an adaptive transform to obtain at least one transformed measurement signal, the adaptive transform being dependent on previously acquired history data;

a calculating unit configured to form a diagnostic index which is dependent on the at least one transformed measurement signal, the diagnostic index serving as a measure of the clinical state of the subject;

a monitoring unit configured to detect a predetermined event; and

a controller configured to replace at least part of the previously acquired history data on which the adaptive transform is currently dependent with other previously acquired history data, the controller being responsive to the monitoring unit.

21. A computer program product for determining a clinical state of a subject, the computer program product comprising:

a first program code portion configured to receive at least one measurement signal containing physiological data of a subject;

a second program code portion configured to subject the measurement signal to at least one adaptive transform, to obtain at least one transformed measurement signal, the adaptive transform being dependent on previously acquired history data;

a third program code portion configured to produce a diagnostic index which is dependent on the transformed measurement signal, the diagnostic index serving as a measure of the clinical state of the subject;

a fourth program code portion configured to detect a predetermined event; and

a fifth program code portion configured to replace at least part of the previously acquired history data on which the adaptive transform is currently dependent with other previously acquired history data, the fifth program code portion being responsive to the fourth program code portion.